Training, sure, but that's buy once cry once.
Whether this means it's a good idea, I don't think so, but the energy usage for parsing isn't why.
> energy usage for parsing isn't why
You'll need to provide actual figures and benchmark these against an actual parser.
I've written parsers for larger-scale server stuff. And while I too don't have these benchmarks available, I'll dare to wager quite a lot that a dedicated parser for almost anything will outperform an LLM magnitudes. I won't be suprised if a parser written in rust uses upwards of 10k times less energy than the most efficient LLM setup today. Hell, even a sed/awk/bash monstrosity probably outperforms such an LLM hundreds of times, energy wise.
This is the kind of thinking that leads to modern software being slower than software from 30 years ago, even though it is running on hardware that's hundreds of times faster.
LLM's are not the solutions, they are the source of big troubles.
You're assuming OP needs an LLM to write a parser, since they mentions writing many during their career they probably don't need it ;)
For small problems it’s not worthwhile, for large problems it is.
It’s similar to choosing to manually do something vs automate it.
Especially since the parser(s) I wrote were rather straightforward finite state machines with stream handling in front, parallel/async tooling around it, and at the core business logic (domain).
Streaming, job/thread/mutex management, FSM are all solved and clear. And I'm convinced an LLM like copilot is very good at writing code for things that have been solved.
The LLM, however, would get very much in the way in the domain/business layer. Because it hasn't got the statistical body of examples to handle our case.
(Parsers I wrote were a.o.: IBAN, gps-trails, user-defined-calculations (simple math formulas), and a DSL to describe hierarchies. I wrote them in Ruby, PHP, rust and perl.)
Of course you were already saying it’s not a good idea, but I think the above definitely plays a role at scale as well.